diff --git a/CHANGELOG.md b/CHANGELOG.md
index fc52dd2..64e757d 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,8 @@
 # Changelog
 
+## Version 1.0.9 - 2025-06
+- Fix bug when dropping rows during the preprocessing
+
 ## Version 1.0.8 - 2022-09-13
 - In the model view, use the code env that was used to train the model
   - No need to build a Python 3.6 code env anymore
diff --git a/plugin.json b/plugin.json
index c7a9a08..be321fb 100755
--- a/plugin.json
+++ b/plugin.json
@@ -1,10 +1,10 @@
 {
     "id": "model-fairness-report",
-    "version": "1.0.8",
+    "version": "1.0.9",
     "meta": {
         "label": "Model Fairness Report",
         "description": "Get insight on the fairness of a model.",
-        "author": "Dataiku (Du PHAN)",
+        "author": "Dataiku",
         "icon": "icon-group",
         "licenseInfo": "Apache Software License",
         "url": "https://www.dataiku.com/product/plugins/model-fairness-report/",
diff --git a/python-lib/dku_webapp/utils.py b/python-lib/dku_webapp/utils.py
index 1a867b4..df01eee 100644
--- a/python-lib/dku_webapp/utils.py
+++ b/python-lib/dku_webapp/utils.py
@@ -93,13 +93,13 @@ def get_histograms(model_accessor, advantageous_outcome, sensitive_column):
     test_df = raw_test_df.dropna(subset=[sensitive_column])
     target_variable = model_accessor.get_target_variable()
 
-    y_true = test_df.loc[:, target_variable]
     pred_df = model_accessor.predict(test_df)
+    y_true = test_df.iloc[pred_df.index].loc[:, target_variable]
     y_pred = pred_df.loc[:, DkuWebappConstants.PREDICTION]
 
     advantageous_outcome_proba_col = 'proba_{}'.format(advantageous_outcome)
     y_pred_proba = pred_df.loc[:, advantageous_outcome_proba_col]
-    sensitive_feature_values = test_df[sensitive_column]
+    sensitive_feature_values = test_df.iloc[pred_df.index][sensitive_column]
 
     return get_histogram_data(y_true, y_pred, y_pred_proba, advantageous_outcome, sensitive_feature_values)
 
@@ -109,11 +109,10 @@ def get_metrics(model_accessor, advantageous_outcome, sensitive_column, referenc
     target_variable = model_accessor.get_target_variable()
     test_df.dropna(subset=[sensitive_column, target_variable], how='any', inplace=True)
 
-    y_true = test_df.loc[:, target_variable]
     pred_df = model_accessor.predict(test_df)
+    y_true = test_df.iloc[pred_df.index].loc[:, target_variable]
     y_pred = pred_df.loc[:, DkuWebappConstants.PREDICTION]
 
-
     try: # check whether or not the column can be casted to int
         if np.array_equal(test_df[sensitive_column], test_df[sensitive_column].astype(int)):
             test_df[sensitive_column] = test_df[sensitive_column].astype(int)
@@ -124,8 +123,8 @@ def get_metrics(model_accessor, advantageous_outcome, sensitive_column, referenc
     except Exception as e:
         logger.info('Sensitive column can not be casted to int. ', e)
         pass
-
-    sensitive_feature_values = test_df[sensitive_column]
+    
+    sensitive_feature_values = test_df.iloc[pred_df.index][sensitive_column]
     model_report = ModelFairnessMetricReport(y_true, y_pred, sensitive_feature_values, advantageous_outcome)
     population_names = sensitive_feature_values.unique()